English
Related papers

Related papers: Structure-Preserving Neural Ordinary Differential …

200 papers

This paper investigates the mean square exponential stabilization problem for a class of coupled PDE-ODE systems with Markov jump parameters. The considered system consists of multiple coupled hyperbolic PDEs and a finite-dimensional ODE,…

Optimization and Control · Mathematics 2025-08-06 Kaijing Lyu , Umberto Biccari , Junmin Wang

A new explicit stabilized scheme of weak order one for stiff and ergodic stochastic differential equations (SDEs) is introduced. In the absence of noise, the new method coincides with the classical deterministic stabilized scheme (or…

Numerical Analysis · Mathematics 2018-06-28 Assyr Abdulle , Ibrahim Almuslimani , Gilles Vilmart

Neural-ODE parameterize a differential equation using continuous depth neural network and solve it using numerical ODE-integrator. These models offer a constant memory cost compared to models with discrete sequence of hidden layers in which…

Machine Learning · Computer Science 2025-03-27 Sheikh Waqas Akhtar

Neural CDEs provide a natural way to process the temporal evolution of irregular time series. The number of function evaluations (NFE) is these systems' natural analog of depth (the number of layers in traditional neural networks). It is…

Machine Learning · Computer Science 2026-01-27 Ilya Kuleshov , Evgenia Romanenkova , Vladislav Zhuzhel , Galina Boeva , Evgeni Vorsin , Alexey Zaytsev

Learning complex dynamics driven by partial differential equations directly from data holds great promise for fast and accurate simulations of complex physical systems. In most cases, this problem can be formulated as an operator learning…

Machine Learning · Computer Science 2024-10-03 Nacime Bouziani , Nicolas Boullé

Neural ordinary differential equations (Neural ODEs) are an effective framework for learning dynamical systems from irregularly sampled time series data. These models provide a continuous-time latent representation of the underlying…

Machine Learning · Computer Science 2023-03-06 Edward De Brouwer , Rahul G. Krishnan

In this work, we rigorously investigate the robustness of graph neural fractional-order differential equation (FDE) models. This framework extends beyond traditional graph neural (integer-order) ordinary differential equation (ODE) models…

Machine Learning · Computer Science 2024-03-05 Qiyu Kang , Kai Zhao , Yang Song , Yihang Xie , Yanan Zhao , Sijie Wang , Rui She , Wee Peng Tay

Residual neural networks are state-of-the-art deep learning models. Their continuous-depth analog, neural ordinary differential equations (ODEs), are also widely used. Despite their success, the link between the discrete and continuous…

Machine Learning · Statistics 2024-07-08 Pierre Marion , Yu-Han Wu , Michael E. Sander , Gérard Biau

Neural Ordinary Differential Equations (NODEs) have proven successful in learning dynamical systems in terms of accurately recovering the observed trajectories. While different types of sparsity have been proposed to improve robustness, the…

Machine Learning · Computer Science 2022-10-27 Hananeh Aliee , Till Richter , Mikhail Solonin , Ignacio Ibarra , Fabian Theis , Niki Kilbertus

Deformable image registration (DIR), aiming to find spatial correspondence between images, is one of the most critical problems in the domain of medical image analysis. In this paper, we present a novel, generic, and accurate diffeomorphic…

Computer Vision and Pattern Recognition · Computer Science 2023-02-08 Yifan Wu , Tom Z. Jiahao , Jiancong Wang , Paul A. Yushkevich , M. Ani Hsieh , James C. Gee

This work proposes a nonlinear finite element method whose nodal values preserve bounds known for the exact solution. The discrete problem involves a nonlinear projection operator mapping arbitrary nodal values into bound-preserving ones…

Numerical Analysis · Mathematics 2023-04-04 Gabriel Barrenechea , Emmanuil Georgoulis , Tristan Pryer , Andreas Veeser

Deep learning has an increasing impact to assist research, allowing, for example, the discovery of novel materials. Until now, however, these artificial intelligence techniques have fallen short of discovering the full differential equation…

We propose a Dynamical System (DS) approach to learn complex, possibly periodic motion plans from kinesthetic demonstrations using Neural Ordinary Differential Equations (NODE). To ensure reactivity and robustness to disturbances, we…

Robotics · Computer Science 2025-08-29 Farhad Nawaz , Tianyu Li , Nikolai Matni , Nadia Figueroa

Traditional approaches to stabilizing hyperbolic PDEs, such as PDE backstepping, often encounter challenges when dealing with high-dimensional or complex nonlinear problems. Their solutions require high computational and analytical costs.…

Analysis of PDEs · Mathematics 2024-11-08 Xianhe Zhang , Yu Xiao , Xiaodong Xu , Biao Luo

Differential equations (DE) constrained optimization plays a critical role in numerous scientific and engineering fields, including energy systems, aerospace engineering, ecology, and finance, where optimal configurations or control…

Machine Learning · Computer Science 2024-10-03 Vincenzo Di Vito , Mostafa Mohammadian , Kyri Baker , Ferdinando Fioretto

Implicit neural networks, a.k.a., deep equilibrium networks, are a class of implicit-depth learning models where function evaluation is performed by solving a fixed point equation. They generalize classic feedforward models and are…

Machine Learning · Computer Science 2022-01-27 Saber Jafarpour , Alexander Davydov , Anton V. Proskurnikov , Francesco Bullo

The existence, uniqueness, and exponential stability results for mild solutions to the fractional neutral stochastic differential system are presented in this article. To demonstrate the results, the concept of bounded integral contractors…

Dynamical Systems · Mathematics 2024-02-16 Dimplekumar Chalishajar , K. Dhanalakshmi , K. Ramkumar , K. Ravikumar

Motivated by classical work on the numerical integration of ordinary differential equations we present a ResNet-styled neural network architecture that encodes non-expansive (1-Lipschitz) operators, as long as the spectral norms of the…

Recurrent neural networks (RNNs) are particularly well-suited for modeling long-term dependencies in sequential data, but are notoriously hard to train because the error backpropagated in time either vanishes or explodes at an exponential…

Machine Learning · Computer Science 2019-08-28 Anil Kag , Ziming Zhang , Venkatesh Saligrama

Neural ODEs (NODEs) are continuous-time neural networks (NNs) that can process data without the limitation of time intervals. They have advantages in learning and understanding the evolution of complex real dynamics. Many previous works…

Machine Learning · Computer Science 2024-11-05 Wenjie Mei , Dongzhe Zheng , Shihua Li